A Comparison of Machine Learning Techniques for the Detection of Type-2 Diabetes Mellitus: Experiences from Bangladesh

Abstract

Diabetes is a chronic disease caused by a persistently high blood sugar level, causing other chronic diseases, including cardiovascular, kidney, eye, and nerve damage. Prompt detection plays a vital role in reducing the risk and severity associated with diabetes, and identifying key risk factors can help individuals become more mindful of their lifestyles. In this study, we conducted a questionnaire-based survey utilizing standard diabetes risk variables to examine the prevalence of diabetes in Bangladesh. To enable prompt detection of diabetes, we compared different machine learning techniques and proposed an ensemble-based machine learning framework that incorporated algorithms such as decision tree, random forest, and extreme gradient boost algorithms. In order to address class imbalance within the dataset, we initially applied the synthetic minority oversampling technique (SMOTE) and random oversampling (ROS) techniques. We evaluated the performance of various classifiers, including decision tree (DT), logistic regression (LR), support vector machine (SVM), gradient boost (GB), extreme gradient boost (XGBoost), random forest (RF), and ensemble technique (ET), on our diabetes datasets. Our experimental results showed that the ET outperformed other classifiers; to further enhance its effectiveness, we fine-tuned and evaluated the hyperparameters of the ET. Using statistical and machine learning techniques, we also ranked features and identified that age, extreme thirst, and diabetes in the family are significant features that prove instrumental in the detection of diabetes patients. This method has great potential for clinicians to effectively identify individuals at risk of diabetes, facilitating timely intervention and care.

Interpretable Machine Learning Framework to Predict the Glass Transition Temperature of Polymers

“…Conversely, when the p -value falls below 0.05, it indicates a probable correlation between the category attributes and the dependent variable. The equation for χ 2 is given below: where the observed frequencies are denoted as , the predicted frequencies are denoted as , and the sample size is denoted as n [ 39 ].…”

Adapted Deep Ensemble Learning-Based Voting Classifier for Osteosarcoma Cancer Classification

“…The evaluation techniques used in this study are based on measures obtained from [62], namely Accuracy (AY), Precision (PN), Recall (RL), F-Measure (FE), Kappa (KA), Log-Loss (LS) and class-specific AUC ROC curves, and Confusion Matrix. These metrics serve as significant benchmarks for assessing the results of the experiment.…”

“…The most significant probability-based order unit of measurement is log-loss. The log-loss metric quantifies the uncertainty of a probabilistic approach by evaluating its accuracy in predicting true labels [62]. A low log-loss value suggests an accurate prediction.…”

Highly Imbalanced Classification of Gout Using Data Resampling and Ensemble Method

“…In order to improve the survival rate of heart failure patients, the extra tree classifier (ETC) was proposed; it uses SMOTE to balance the data [25]. Also, the authors used SMOTE to classify diabetes and reliable stress levels [26,27]. Fitriyani et al proposed using extreme gradient boosting with SMOTE-ENN to solve the cardiovascular prediction problem [28].…”

“…Classification on imbalanced datasets can result in biased outcomes, as most standard classification algorithms favor the majority class, leading to poor prediction accuracy for the minority class. To balance the data distribution, most prior studies employed the SMOTE method [24][25][26][27][28], which has some disadvantages. The quality of the samples generated by SMOTE depends on the parameter k, which is difficult to determine due to the variety of datasets.…”